1,721,025 research outputs found
MedicoSAM: Towards foundation models for medical image segmentation
No full textMedical image segmentation is an important analysis task in clinical practice and research. Deep learning has massively advanced the field, but current approaches are mostly based on models trained for a specific task. Training such models or adapting them to a new condition is costly due to the need for (manually) labeled data. The emergence of vision foundation models, especially Segment Anything, offers a path to universal segmentation for medical images, overcoming these issues. Here, we study how to improve Segment Anything for medical images by comparing different finetuning strategies on a large and diverse dataset. We evaluate the finetuned models on a wide range of interactive and (automatic) semantic segmentation tasks. We find that the performance can be clearly improved for interactive segmentation. However, semantic segmentation does not benefit from pretraining on medical images. Our best model, MedicoSAM, is publicly available at https://github.com/computational-cell-analytics/medico-sam. We show that it is compatible with existing tools for data annotation and believe that it will be of great practical value
Conférence: La damnatio memoriae du pape Constantin II et le concile de Rome (769)
No full textLa prochaine séance du séminaire d’histoire médiévale organisé par l’École pratique des hautes études (Laurent Morelle) et l’Institut historique allemand (Rolf Große) se tiendra le mercredi 19 octobre 2016 de 10h00 à 12h00 à l’IHA, 8 rue du Parc-Royal, 75003 Paris. Au programme: Rosamond McKitterick (université Cambridge): La damnatio memoriae du pape Constantin II et le concile de Rome (769) Présidence: Michel Sot (université Paris-Sorbonne
Conférence: La damnatio memoriae du pape Constantin II et le concile de Rome (769)
No full textLa prochaine séance du séminaire d’histoire médiévale organisé par l’École pratique des hautes études (Laurent Morelle) et l’Institut historique allemand (Rolf Große) se tiendra le mercredi 19 octobre 2016 de 10h00 à 12h00 à l’IHA, 8 rue du Parc-Royal, 75003 Paris. Au programme: Rosamond McKitterick (université Cambridge): La damnatio memoriae du pape Constantin II et le concile de Rome (769) Présidence: Michel Sot (université Paris-Sorbonne
A Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation
No full textWe propose a novel theoretical framework that generalizes algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations, and introduce new algorithms for combinations which have not been studied. An extensive comparison is performed to evaluate properties of the clustering algorithms in the context of instance segmentation in images, including robustness to noise and efficiency. We show how one of the new algorithms proposed in our framework outperforms all previously known agglomerative methods for signed graphs, both on the competitive CREMI 2016 EM segmentation benchmark and on the CityScapes dataset
GASP, a generalized framework for agglomerative clustering of signed graphs and its application to Instance Segmentation
No full textThe Mutex Watershed and its Objective: Efficient, Parameter-Free Graph Partitioning
No full textImage partitioning, or segmentation without semantics, is the task of decomposing an image into distinct segments, or equivalently to detect closed contours. Most prior work either requires seeds, one per segment; or a threshold; or formulates the task as multicut / correlation clustering, an NP-hard problem. Here, we propose an efficient algorithm for graph partitioning, the "Mutex Watershed". Unlike seeded watershed, the algorithm can accommodate not only attractive but also repulsive cues, allowing it to find a previously unspecified number of segments without the need for explicit seeds or a tunable threshold. We also prove that this simple algorithm solves to global optimality an objective function that is intimately related to the multicut / correlation clustering integer linear programming formulation. The algorithm is deterministic, very simple to implement, and has empirically linearithmic complexity. When presented with short-range attractive and long-range repulsive cues from a deep neural network, the Mutex Watershed gives the best results currently known for the competitive ISBI 2012 EM segmentation benchmark
Wrapped up: advancements in volume electron microscopy and application in myelin research
No full textA Generalized Framework for Agglomerative Clustering of Signed Graphs applied to Instance Segmentation
No full textWe propose a novel theoretical framework that generalizes algorithms for hierarchical agglomerative clustering to weighted graphs with both attractive and repulsive interactions between the nodes. This framework defines GASP, a Generalized Algorithm for Signed graph Partitioning, and allows us to explore many combinations of different linkage criteria and cannot-link constraints. We prove the equivalence of existing clustering methods to some of those combinations, and introduce new algorithms for combinations which have not been studied. An extensive comparison is performed to evaluate properties of the clustering algorithms in the context of instance segmentation in images, including robustness to noise and efficiency. We show how one of the new algorithms proposed in our framework outperforms all previously known agglomerative methods for signed graphs, both on the competitive CREMI 2016 EM segmentation benchmark and on the CityScapes dataset
Tiling artifacts and trade-offs of feature normalization in the segmentation of large biological images
No full textSegmentation of very large images is a common problem in microscopy, medical imaging or remote sensing. The problem is usually addressed by sliding window inference, which can theoretically lead to seamlessly stitched predictions. However, in practice many of the popular pipelines still suffer from tiling artifacts. We investigate the root cause of these issues and show that they stem from the normalization layers within the neural networks. We propose indicators to detect normalization issues and further explore the trade-offs between artifact-free and high-quality predictions, using three diverse microscopy datasets as examples. Finally, we propose to use BatchRenorm as the most suitable normalization strategy, which effectively removes tiling artifacts and enhances transfer performance, thereby improving the reusability of trained networks for new datasets
- …
